Linear Bayesian Reinforcement Learning

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

In this paper, we study sampling from a posterior derived from a neural network. We propose a new probabilistic model consisting of adding noise at every pre- and post-activation in the network, arguing that the resulting posterior can be sampled using an ...

Modern integrated circuits are tiny yet incredibly complex technological artifacts, composed of millions and billions of individual structures working in unison. Managing their complexity and facilitating their design drove part of the co-evolution of mode ...

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

Surrogate-based optimization is widely used for aerodynamic shape optimization, and its effectiveness depends on representative sampling of the design space. However, traditional sampling methods are hard-pressed to effectively sample high-dimensional desi ...

The recent geopolitical conflicts in Europe have underscored the vulnerability of the current energy system to the volatility of energy carrier prices. In the prospect of defining robust energy systems ensuring sustainable energy supply in the future, the ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

Whereas the ability of deep networks to produce useful predictions on many kinds of data has been amply demonstrated, estimating the reliability of these predictions remains challenging. Sampling approaches such as MC-Dropout and Deep Ensembles have emerge ...

In light of the challenges posed by climate change and the goals of the Paris Agreement, electricity generation is shifting to a more renewable and decentralized pattern, while the operation of systems like buildings is increasingly electrified. This calls ...

In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...

Modern computing has enhanced our understanding of how social interactions shape collective behaviour in animal societies. Although analytical models dominate in studying collective behaviour, this study introduces a deep learning model to assess social in ...

We propose a novel approach to evaluating the ionic Seebeck coefficient in electrolytes from relatively short equilibrium molecular dynamics simulations, based on the Green-Kubo theory of linear response and Bayesian regression analysis. By exploiting the ...

There is a bias in the inference pipeline of most diffusion models. This bias arises from a signal leak whose distribution deviates from the noise distribution, creating a discrepancy between training and inference processes. We demonstrate that this signa ...

In this work, various methods were used to improve the printability of a photocurable polyvinylsilazane resin filled with silicon nitride particles for digital light processing. The developed resin was used as a preceramic polymer for polymer-to-ceramic co ...

The upcoming Square Kilometre Array Observatory will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as ...

Epilepsy, a major neurological disease, requires careful diagnosis and treatment. However, the detection of epileptic seizures remains a significant challenge. Current clinical practice relies on expert analysis of EEG signals, a process that is time-consu ...

In this thesis we explore the applications of projective geometry, a mathematical theory of the relation between 3D scenes and their 2D images, in modern learning-based computer vision systems. This is an interesting research question which contradicts the ...

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

Decentralized learning is appealing as it enables the scalable usage of large amounts of distributed data and resources (without resorting to any central entity), while promoting privacy since every user minimizes the direct exposure of their data. Yet, wi ...

Sample efficiency is a fundamental challenge in de novo molecular design. Ideally, molecular generative models should learn to satisfy a desired objective under minimal calls to oracles (computational property predictors). This problem becomes more apparen ...

Linear Bayesian Reinforcement Learning

Chat with Graph Search

Gibbs sampling the posterior of neural networks

Graph generative deep learning models with an application to circuit topologies

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

DiffAirfoil: An Efficient Novel Airfoil Sampler Based on Latent Space Diffusion Model for Aerodynamic Shape Optimization

Identification of typical district configurations: A two-step global sensitivity analysis framework

Random matrix methods for high-dimensional machine learning models

ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference

Quantifying the Unknown: Data-Driven Approaches and Applications in Energy Systems

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

Predicting the long-term collective behaviour of fish pairs with deep learning

Seebeck Coefficient of Ionic Conductors from Bayesian Regression Analysis

Exploiting the Signal-Leak Bias in Diffusion Models

Influence of Si3N4 fillers and pyrolysis profile on the microstructure of additively manufactured silicon carbonitride ceramics derived from polyvinylsilazane

Deep learning approach for identification of H II regions during reionization in 21-cm observations - II. Foreground contamination

Resource-Efficient Continual Learning for Personalized Online Seizure Detection

Incorporating Projective Geometry into Deep Learning

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

The Privacy Power of Correlated Noise in Decentralized Learning

Augmented Memory: Sample-Efficient Generative Molecular Design with Reinforcement Learning